© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 46703
    Prev
    Next
    INDEX
    Explanations

    Mini brands and models

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_13_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    АЗ
    0.57
    器
    0.52
    ση
    0.51
     VEH
    0.48
    قق
    0.47
    უნქ
    0.47
    ﻒ
    0.47
    偶
    0.46
    ᓕ
    0.46
    ᓐ
    0.46
    POSITIVE LOGITS
    ee
    0.62
    ense
    0.61
    oy
    0.59
    ie
    0.59
    ose
    0.59
    za
    0.58
    Pl
    0.58
    ora
    0.58
    oo
    0.57
    yl
    0.56
    Activations Density 0.008%

    No Known Activations